aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorMuriithi Frederick Muriuki2021-08-27 15:55:41 +0300
committerMuriithi Frederick Muriuki2021-08-27 15:55:41 +0300
commita9fa309f4017d84cd30f6df90376042f20b1836b (patch)
tree695a353cd35b9736c7f8453d44d3e2b5143f1261
parent28fde00ee2835d404157652548a4265be3accede (diff)
downloadgenenetwork3-a9fa309f4017d84cd30f6df90376042f20b1836b.tar.gz
Test out generation of traits file
Issue: https://github.com/genenetwork/gn-gemtext-threads/blob/main/topics/gn1-migration-to-gn2/clustering.gmi * As part of the development effort, this commit provides a proof-of-concept as a reference for generating the traits data file. It might be useful for verifying that the functions that are called are working as is expected.
-rw-r--r--qtlfilesexport.py67
1 files changed, 67 insertions, 0 deletions
diff --git a/qtlfilesexport.py b/qtlfilesexport.py
new file mode 100644
index 0000000..2e7c9c2
--- /dev/null
+++ b/qtlfilesexport.py
@@ -0,0 +1,67 @@
+"""
+Test the qtlfiles export of traits files
+
+Run with:
+
+ env SQL_URI="mysql://<user>:<password>@<host>:<port>/db_webqtl" python3 qtlfilesexport.py
+
+replacing the variables in the angled brackets with the appropriate values
+"""
+import random
+import string
+from gn3.computations.slink import slink
+from gn3.db_utils import database_connector
+from gn3.computations.heatmap import export_trait_data
+from gn3.db.traits import retrieve_trait_data, retrieve_trait_info
+from gn3.computations.heatmap import (
+ cluster_traits,
+ compute_heatmap_order,
+ generate_traits_file,
+ retrieve_strains_and_values)
+
+TMPDIR = "tmp/qtltests"
+
+def trait_fullnames():
+ """Return sample names for traits"""
+ return [
+ "UCLA_BXDBXH_CARTILAGE_V2::ILM103710672",
+ "UCLA_BXDBXH_CARTILAGE_V2::ILM2260338",
+ "UCLA_BXDBXH_CARTILAGE_V2::ILM3140576",
+ "UCLA_BXDBXH_CARTILAGE_V2::ILM5670577",
+ "UCLA_BXDBXH_CARTILAGE_V2::ILM2070121",
+ "UCLA_BXDBXH_CARTILAGE_V2::ILM103990541",
+ "UCLA_BXDBXH_CARTILAGE_V2::ILM1190722",
+ "UCLA_BXDBXH_CARTILAGE_V2::ILM6590722",
+ "UCLA_BXDBXH_CARTILAGE_V2::ILM4200064",
+ "UCLA_BXDBXH_CARTILAGE_V2::ILM3140463"]
+
+def random_string(length):
+ return "".join(
+ random.choices(
+ string.ascii_letters + string.digits, k=length))
+
+def main():
+ """entrypoint function"""
+ conn = database_connector()[0]
+ threshold = 0
+ traits = [
+ retrieve_trait_info(threshold, fullname, conn)
+ for fullname in trait_fullnames()]
+ traits_data_list = [retrieve_trait_data(t, conn) for t in traits]
+ strains = list(set([k for td in traits_data_list for k in td["data"].keys()]))
+ exported_traits_data_list = [
+ export_trait_data(td, strains) for td in traits_data_list]
+ slinked = slink(cluster_traits(exported_traits_data_list))
+ orders = compute_heatmap_order(slinked)
+ strains_and_values = retrieve_strains_and_values(
+ orders, strains, exported_traits_data_list)
+ strains_values = strains_and_values[0][1]
+ strains_values2 = strains_and_values[1][1]
+ trait_values = [t[2] for t in strains_and_values]
+ traits_filename = "{}/traits_test_file_{}.txt".format(
+ TMPDIR, random_string(10))
+ generate_traits_file(strains_values, trait_values, traits_filename)
+ print("Generated file: {}".format(traits_filename))
+
+if __name__ == "__main__":
+ main()